mirror of
https://github.com/microsoft/graphrag.git
synced 2025-07-16 05:21:07 +00:00
3b09df6e07
* Migrate towards using static output directories
- Fixes load_config eagering resolving directories.
Directories are only resolved when the output
directories are local.
- Add support for `--output` and `--reporting` flags
for index CLI. To achieve previous output structure
`index --output run1/artifacts --reports run1/reports`.
- Use static output directories when initializing
a new project.
- Maintains backward compatibility for those using
timestamp outputs locally.
* fix smoke tests
* update query cli to work with static directories
* remove eager path resolution from load_config. Support CLI overrides that can be resolved.
* add docs and output logs/artifacts to same directory
* use match statement
* switch back to if statement
---------
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
1.9 KiB
1.9 KiB
| title | navtitle | layout | tags | date | ||
|---|---|---|---|---|---|---|
| Indexer CLI | CLI | page |
|
2023-01-03 |
The GraphRAG indexer CLI allows for no-code usage of the GraphRAG Indexer.
python -m graphrag.index --verbose --root </workspace/project/root> --config <custom_config.yml>
--resume <timestamp> --reporter <rich|print|none> --emit json,csv,parquet
--nocache
CLI Arguments
--verbose- Adds extra logging information during the run.--root <data-project-dir>- the data root directory. This should contain aninputdirectory with the input data, and an.envfile with environment variables. These are described below.--init- This will initialize the data project directory at the specifiedrootwith bootstrap configuration and prompt-overrides.--resume <output-timestamp>- if specified, the pipeline will attempt to resume a prior run. The parquet files from the prior run will be loaded into the system as inputs, and the workflows that generated those files will be skipped. The input value should be the timestamped output folder, e.g. "20240105-143721".--config <config_file.yml>- This will opt-out of the Default Configuration mode and execute a custom configuration. If this is used, then none of the environment-variables below will apply.--reporter <reporter>- This will specify the progress reporter to use. The default isrich. Valid values arerich,print, andnone.--emit <types>- This specifies the table output formats the pipeline should emit. The default isparquet. Valid values areparquet,csv, andjson, comma-separated.--nocache- This will disable the caching mechanism. This is useful for debugging and development, but should not be used in production.--output <directory>- Specify the output directory for pipeline artifacts.--reports <directory>- Specify the output directory for reporting.